Research map / Learning theory and algorithms / Matrix and tensor methods
Expected Frequency Matrices of Elections: Computation, Geometry, and Preference Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Fit Mallows, φ-Walsh, and φ-Conitzer by minimizing positionwise distance to expected frequency matrices | 165 real-world elections · Real-world election datasets | average normalized positionwise distance: 0.14 | Helped |
| Use Mallows rather than the closest among Mallows, φ-Walsh, and φ-Conitzer | 165 real-world elections · Real-world election datasets | average normalized positionwise distance: 0.0007 higher | Hurt |
| Fit with φ-Walsh instead of the best of the three distributions | 165 real-world elections · Real-world election datasets | average normalized positionwise distance: 0.03 higher | Hurt |
| Fit with φ-Conitzer instead of the best of the three distributions | 165 real-world elections · Real-world election datasets | average normalized positionwise distance | Hurt |
| Estimate Mallows dispersion by minimizing frequency-matrix distance rather than using the Kemeny-based MLE | Mallows parameter estimation · 165 real-world elections | Pearson correlation: 0.976 | No clear effect |
| Add a reversed-central-vote Mallows mixture (ablation) | Mallows fitting · 165 real-world elections | average minimum normalized positionwise distance: around 0.02 | Helped |
| Use the frequency-matrix fitting approach instead of maximum-likelihood estimation | Mallows dispersion estimation · 165 real-world elections | average absolute difference from Kemeny MLE dispersion: 0.02 | No clear effect |
Closest papers by meaning
- Can We Predict the Election Outcome from Sampled Votes? (AAAI 2020 · similarity 0.89)
- Exact Learning of Preference Structure: Single-peaked Preferences and Beyond (ICML 2022 · similarity 0.87)
- Approximate Inference of Outcomes in Probabilistic Elections (AAAI 2019 · similarity 0.86)
- Properties of Position Matrices and Their Elections (AAAI 2023 · similarity 0.86)
- Spatial Voting with Incomplete Voter Information (AAAI 2024 · similarity 0.85)
- Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound (NeurIPS 2021 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.